a Sic?:@sdZddlmmZddlmZddlmZddlmZddlm Z ddl m Z ddl m Z dd lmZdd lmZdd lmZed d GdddeZeZdS)zGKeras 3D transposed convolution layer (sometimes called deconvolution).N) activations) constraints) initializers) regularizers)utils) InputSpec)Conv3D) conv_utils) keras_exportzkeras.layers.Conv3DTransposez#keras.layers.Convolution3DTransposecsLeZdZdZejdfdd Zd d Zd d ZddZ fddZ Z S)Conv3DTransposeaTransposed convolution layer (sometimes called Deconvolution). The need for transposed convolutions generally arises from the desire to use a transformation going in the opposite direction of a normal convolution, i.e., from something that has the shape of the output of some convolution to something that has the shape of its input while maintaining a connectivity pattern that is compatible with said convolution. When using this layer as the first layer in a model, provide the keyword argument `input_shape` (tuple of integers or `None`, does not include the sample axis), e.g. `input_shape=(128, 128, 128, 3)` for a 128x128x128 volume with 3 channels if `data_format="channels_last"`. Args: filters: Integer, the dimensionality of the output space (i.e. the number of output filters in the convolution). kernel_size: An integer or tuple/list of 3 integers, specifying the depth, height and width of the 3D convolution window. Can be a single integer to specify the same value for all spatial dimensions. strides: An integer or tuple/list of 3 integers, specifying the strides of the convolution along the depth, height and width. Can be a single integer to specify the same value for all spatial dimensions. Specifying any stride value != 1 is incompatible with specifying any `dilation_rate` value != 1. padding: one of `"valid"` or `"same"` (case-insensitive). `"valid"` means no padding. `"same"` results in padding with zeros evenly to the left/right or up/down of the input such that output has the same height/width dimension as the input. output_padding: An integer or tuple/list of 3 integers, specifying the amount of padding along the depth, height, and width. Can be a single integer to specify the same value for all spatial dimensions. The amount of output padding along a given dimension must be lower than the stride along that same dimension. If set to `None` (default), the output shape is inferred. data_format: A string, one of `channels_last` (default) or `channels_first`. The ordering of the dimensions in the inputs. `channels_last` corresponds to inputs with shape `(batch_size, depth, height, width, channels)` while `channels_first` corresponds to inputs with shape `(batch_size, channels, depth, height, width)`. It defaults to the `image_data_format` value found in your Keras config file at `~/.keras/keras.json`. If you never set it, then it will be "channels_last". dilation_rate: an integer or tuple/list of 3 integers, specifying the dilation rate to use for dilated convolution. Can be a single integer to specify the same value for all spatial dimensions. Currently, specifying any `dilation_rate` value != 1 is incompatible with specifying any stride value != 1. activation: Activation function to use. If you don't specify anything, no activation is applied (see `keras.activations`). use_bias: Boolean, whether the layer uses a bias vector. kernel_initializer: Initializer for the `kernel` weights matrix (see `keras.initializers`). Defaults to 'glorot_uniform'. bias_initializer: Initializer for the bias vector (see `keras.initializers`). Defaults to 'zeros'. kernel_regularizer: Regularizer function applied to the `kernel` weights matrix (see `keras.regularizers`). bias_regularizer: Regularizer function applied to the bias vector (see `keras.regularizers`). activity_regularizer: Regularizer function applied to the output of the layer (its "activation") (see `keras.regularizers`). kernel_constraint: Constraint function applied to the kernel matrix (see `keras.constraints`). bias_constraint: Constraint function applied to the bias vector (see `keras.constraints`). Input shape: 5D tensor with shape: `(batch_size, channels, depth, rows, cols)` if data_format='channels_first' or 5D tensor with shape: `(batch_size, depth, rows, cols, channels)` if data_format='channels_last'. Output shape: 5D tensor with shape: `(batch_size, filters, new_depth, new_rows, new_cols)` if data_format='channels_first' or 5D tensor with shape: `(batch_size, new_depth, new_rows, new_cols, filters)` if data_format='channels_last'. `depth` and `rows` and `cols` values might have changed due to padding. If `output_padding` is specified:: ``` new_depth = ((depth - 1) * strides[0] + kernel_size[0] - 2 * padding[0] + output_padding[0]) new_rows = ((rows - 1) * strides[1] + kernel_size[1] - 2 * padding[1] + output_padding[1]) new_cols = ((cols - 1) * strides[2] + kernel_size[2] - 2 * padding[2] + output_padding[2]) ``` Returns: A tensor of rank 5 representing `activation(conv3dtranspose(inputs, kernel) + bias)`. Raises: ValueError: if `padding` is "causal". ValueError: when both `strides` > 1 and `dilation_rate` > 1. References: - [A guide to convolution arithmetic for deep learning](https://arxiv.org/abs/1603.07285v1) - [Deconvolutional Networks](https://www.matthewzeiler.com/mattzeiler/deconvolutionalnetworks.pdf) r r validNTglorot_uniformzerosc stjf||||||t|| t| t| t| t| t|t|t|d|||_|jdurtj |jdddd|_t |j |jD]*\}}||krt d|j d|jdqdS) N)filters kernel_sizestridespadding data_format dilation_rate activationuse_biaskernel_initializerbias_initializerkernel_regularizerbias_regularizeractivity_regularizerkernel_constraintbias_constraintoutput_paddingT) allow_zeroz>Strides must be greater than output padding. Received strides=z, output_padding=.) super__init__rgetrrrr!r normalize_tuplezipr ValueError)selfrrrrr!rrrrrrrrrrrkwargsstrideout_pad __class__g/var/www/html/django/DPS/env/lib/python3.9/site-packages/keras/layers/convolutional/conv3d_transpose.pyr%sB  zConv3DTranspose.__init__c Cst|}t|dkr&td|d|}|j|jdurTtd|d|dt||}|j|j |f}t d||id|_ |j d||j |j|jd |jd |_|jr|j d |j f|j|j|jd |jd |_nd|_d |_dS) Nz0Inputs should have rank 5. Received input_shape=r#zhThe channel dimension of the inputs to `Conv3DTranspose` should be defined. The input_shape received is z , where axis z> (0-based) is the channel dimension, which found to be `None`.)ndimaxeskernelT)shape initializer regularizer constraint trainabledtypebias)tf TensorShapelenr)_get_channel_axisdimsvalueintrrr input_spec add_weightrrrr;r5rrrrr<built)r* input_shape channel_axis input_dim kernel_shaper0r0r1buildsP     zConv3DTranspose.buildc Cst|}|d}|jdkr(d\}}}n d\}}}||}||}||} |j\} } } |j\} }}|jdurzd}}}n |j\}}}tj|| |j|| d}tj|| |j||d}tj| | |j||d}|jdkr||j |||f}dd| ||f}n|||||j f}d| ||df}t |}tj j ||j ||tj|jdd|jd }tsf||j}|||jrtj j||jtj|jd dd }|jdur||S|S) Nrchannels_first)r )r rMr rr!r,r r2)r3)rrrN)r)r=r6rrrr!r deconv_output_lengthrrstacknnconv3d_transposer5convert_data_formatupperexecuting_eagerlycompute_output_shape set_shaperbias_addr<r)r*inputs inputs_shape batch_sized_axish_axisw_axisdepthheightwidthkernel_dkernel_hkernel_wstride_dstride_hstride_w out_pad_d out_pad_h out_pad_w out_depth out_height out_width output_shaperoutput_shape_tensoroutputs out_shaper0r0r1calls               zConv3DTranspose.callcCst|}t|}|jdkr.d\}}}}n d\}}}}|j\}}} |j\} } } |jdurjd} }}n |j\} }}|j||<t j ||||j | | d||<t j ||||j || d||<t j ||| |j || d||<t|S)NrL)r rMr rN)rNr rMr rO) r=r>as_listlistrrrr!rr rPr)r*rGroc_axisr]r^r_rcrdrerfrgrhrirjrkr0r0r1rWWsB          z$Conv3DTranspose.compute_output_shapecs"t}|d|j|d<|S)Nrr!)r$ get_configpopr!)r*configr.r0r1rws   zConv3DTranspose.get_config)r rNNr NTrrNNNNN) __name__ __module__ __qualname____doc__rallow_initializer_layoutr%rKrsrWrw __classcell__r0r0r.r1r !s*w4+[(r )r}tensorflow.compat.v2compatv2r=kerasrrrr keras.dtensorrkeras.engine.input_specr!keras.layers.convolutional.conv3dr keras.utilsr tensorflow.python.util.tf_exportr r Convolution3DTransposer0r0r0r1s"         f